An MRI Radiomics Approach to Predict the Hypercoagulable Status of Gliomas

Simple Summary: Venous thromboembolic events, such as pulmonary embolism and deep venous thrombosis, are frequent and potentially severe complications of gliomas. It is currently difficult to predict their occurrence, and systematic thromboprophylaxis is not recommended because of the associated risk of bleeding. The establishment of a local hypercoagulable state constitutes the biological rationale for these complications, with a key role played by the overexpression of tissue factor (TF). We examined the possible application of radiomics analyses of tumor MRI to predict the hypercoagulable status of gliomas. Using radiogenomics data from two independent glioma cohorts, we built a model that predicts the most hypercoagulable tumors with good performance. We discuss the potential of radiomics for the prediction of vascular complications and the study of coagulation in gliomas. Venous thromboembolic events are frequent complications of Glioblastoma Multiforme (GBM) and low-grade gliomas (LGGs). The overexpression of tissue factor (TF) plays an essential role in the local hypercoagulable phenotype that underlies these complications. Our aim was to build an MRI radiomics model for the non-invasive exploration of the hypercoagulable status of LGG/GBM. Radiogenomics data from The Cancer Genome Atlas (TCGA) and REMBRANDT (Repository for molecular BRAin Neoplasia DaTa) cohorts were used. A logistic regression model (Radscore) was built in order to identify the top 20% TF-expressing tumors, considered to be at high thromboembolic risk. The most contributive MRI radiomics features from LGG/GBM linked to high TF were identified in TCGA using Least Absolute Shrinkage and Selection Operator (LASSO) regression. A logistic regression model was built, whose performance was analyzed with ROC in the TCGA/training and REMBRANDT/validation cohorts: AUC = 0.87 [CI95: 0.81-0.94, p < 0.0001] and AUC = 0.78 [CI95: 0.56-1.00, p = 0.02], respectively. In agreement with the key role of the coagulation cascade in gliomas, LGG patients with a high Radscore had lower overall and disease-free survival. The Radscore was linked to the presence of specific genomic alterations, the composition of the tumor coagulome and the tumor immune infiltrate. Our findings suggest that a non-invasive assessment of the hypercoagulable status of LGG/GBM is possible with MRI radiomics.